Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 46042
    Prev
    Next
    INDEX
    Explanations

    tentative language that suggests uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    101
    +0.12
    0.5%
    151
    +0.10
    0.4%
    548
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    465
    +0.12
    0.03
    101
    +0.10
    0.03
    687
    +0.09
    0.02
    Negative Logits
    sheet
    -0.79
    iak
    -0.77
    ework
    -0.75
    bender
    -0.74
    cium
    -0.71
    ulty
    -0.70
    idy
    -0.70
    chens
    -0.69
    alez
    -0.69
    cies
    -0.68
    POSITIVE LOGITS
     unsurprisingly
    1.03
    haps
    0.91
     unsur
    0.84
     sensing
    0.79
     surprisingly
    0.76
     analogous
    0.75
     unintentionally
    0.75
     exacerbated
    0.73
     surprising
    0.73
     unwittingly
    0.72
    Activations Density 0.031%

    No Known Activations